RT journal article
T1 Facial attribute-aware DeepFake detection through semi-supervised facial attribute labeling
A1 Stile, Vittorio
A1 Caldelli, Roberto
A1 Balderas Díaz, Sara
A1 Guerrero Contreras, Gabriel José
A1 Medina Bulo, María Inmaculada
A2 Ingeniería Informática
K1 DeepFake detection
K1 FaceForensics++
K1 facial attribute analysis
K1 misclassification analysis
K1 semi-supervised labeling
AB This study investigates the correlation between misclassifications in DeepFake detection and high-level facial attributes. A pre-trained frame-level classifier is used to distinguish manipulated from authentic video content, and its wrong predictions are analyzed in detail. To enrich the dataset, we automatically annotate each video with additional labels, including gender, hair color, hair length, ear visibility, and ethnicity, using a semi-supervised facial-attribute recognition pipeline. We extend this analysis with controlled training-time exclusions on FaceForensics++, keeping a unified test set to isolate generalization bias. Compared to the no-exclusion baseline (Accuracy = 0.806, AUC = 0.823), excluding samples with ears visible yields the largest degradation (Accuracy = 0.741, AUC = 0.763), while excluding non-visible ears has a milder effect (Accuracy = 0.813, AUC = 0.832). Hair length shows a moderate but consistent impact that interacts with ear visibility. We also explain the observed confusion-matrix asymmetry as a consequence of fixed score thresholds and video-level k-of-n aggregation. The results demonstrate that ear visibility is a critical factor for robust FAKE vs. REAL discrimination and motivate attribute-aware training, including targeted data curation, attribute-specific augmentation, and threshold calibration. The proposed framework provides actionable guidance for bias-aware training strategies and supports the development of more interpretable and operationally reliable DeepFake detection systems.
PB Frontiers Media SA
SN 2813-3315
YR 2026
FD 2026-06-24
LK http://hdl.handle.net/10498/39974
UL http://hdl.handle.net/10498/39974
LA eng
DS Repositorio Institucional de la Universidad de Cádiz
RD 05-nov-2026